{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:03:49Z","timestamp":1782759829548,"version":"3.54.5"},"reference-count":80,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2022,7,26]],"date-time":"2022-07-26T00:00:00Z","timestamp":1658793600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,7,26]],"date-time":"2022-07-26T00:00:00Z","timestamp":1658793600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100010909","name":"Young Scientists Fund","doi-asserted-by":"publisher","award":["62106177"],"award-info":[{"award-number":["62106177"]}],"id":[{"id":"10.13039\/501100010909","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2042020KF0016"],"award-info":[{"award-number":["2042020KF0016"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1007\/s00371-022-02603-1","type":"journal-article","created":{"date-parts":[[2022,7,26]],"date-time":"2022-07-26T11:02:51Z","timestamp":1658833371000},"page":"4501-4512","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["Graph-aware transformer for skeleton-based action recognition"],"prefix":"10.1007","volume":"39","author":[{"given":"Jiaxu","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4737-0717","authenticated-orcid":false,"given":"Chao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruide","family":"Tu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhigang","family":"Tu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,7,26]]},"reference":[{"issue":"4","key":"2603_CR1","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1007\/s00371-018-1489-7","volume":"35","author":"S Agahian","year":"2019","unstructured":"Agahian, S., Negin, F., K\u00f6se, C.: Improving bag-of-poses with semi-temporal pose descriptors for skeleton-based action recognition. Visual Comp. 35(4), 519\u2013607 (2019)","journal-title":"Visual Comp."},{"key":"2603_CR2","doi-asserted-by":"crossref","unstructured":"Caetano, C., Br\u00e9mond, F., Schwartz, W.R.: Skeleton image representation for 3d action recognition based on tree structure and reference joints. In: 2019 32nd SIBGRAPI conference on graphics, patterns and images (SIBGRAPI), IEEE, pp 16\u201323 (2019a)","DOI":"10.1109\/SIBGRAPI.2019.00011"},{"key":"2603_CR3","doi-asserted-by":"crossref","unstructured":"Caetano, C., Sena, J., Br\u00e9mond, F., et\u00a0al.: Skelemotion: a new representation of skeleton joint sequences based on motion information for 3d action recognition. In: 2019 16th IEEE International conference on advanced video and signal based surveillance (AVSS), IEEE, pp 1\u20138 (2019c)","DOI":"10.1109\/AVSS.2019.8909840"},{"issue":"11","key":"2603_CR4","doi-asserted-by":"publisher","first-page":"3247","DOI":"10.1109\/TCSVT.2018.2879913","volume":"29","author":"C Cao","year":"2018","unstructured":"Cao, C., Lan, C., Zhang, Y., et al.: Skeleton-based action recognition with gated convolutional neural networks. IEEE Trans. Circuit Sys. Video Tech. 29(11), 3247\u20133257 (2018)","journal-title":"IEEE Trans. Circuit Sys. Video Tech."},{"issue":"99","key":"2603_CR5","first-page":"1","volume":"PP","author":"Z Cao","year":"2018","unstructured":"Cao, Z., Hidalgo, G., Simon, T., et al.: Openpose: realtime multi-person 2d pose estimation using part affinity fields. IEEE Trans. Patt. Anal. & Mach. Intell. PP(99), 1 (2018)","journal-title":"IEEE Trans. Patt. Anal. & Mach. Intell."},{"key":"2603_CR6","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., et\u00a0al.: End-to-end object detection with transformers. In: European Conference on Computer Vision, Springer, Berlin. pp 213\u2013229 (2020b)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2603_CR7","doi-asserted-by":"crossref","unstructured":"Chang, Y., Tu, Z., Xie, W., et\u00a0al.: Clustering driven deep autoencoder for video anomaly detection. In: European conference on computer vision, Springer, Berlin pp 329\u2013345 (2020)","DOI":"10.1007\/978-3-030-58555-6_20"},{"key":"2603_CR8","unstructured":"Chen, H., Wang, Y., Guo, T., et\u00a0al.: Pre-trained image processing transformer. In: arXiv preprint arXiv:2012.00364 (2020)"},{"key":"2603_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, Z., Peng, Y., et\u00a0al.: Cascaded pyramid network for multi-person pose estimation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7103\u20137112 (2018)","DOI":"10.1109\/CVPR.2018.00742"},{"key":"2603_CR10","doi-asserted-by":"crossref","unstructured":"Cheng, K., Zhang, Y., Cao, C., et\u00a0al.: Decoupling gcn with dropgraph module for skeleton-based action recognition. In: Proceedings of the European conference on computer vision (ECCV) (2020a)","DOI":"10.1007\/978-3-030-58586-0_32"},{"key":"2603_CR11","doi-asserted-by":"crossref","unstructured":"Cheng, K., Zhang, Y., He, X., et\u00a0al.: Skeleton-based action recognition with shift graph convolutional network. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 183\u2013192 (2020b)","DOI":"10.1109\/CVPR42600.2020.00026"},{"key":"2603_CR12","doi-asserted-by":"crossref","unstructured":"Crasto, N., Weinzaepfel, P., Alahari, K., et\u00a0al.: Mars: Motion-augmented rgb stream for action recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7882\u20137891 (2019)","DOI":"10.1109\/CVPR.2019.00807"},{"key":"2603_CR13","unstructured":"Dai, Z., Cai, B., Lin, Y., et\u00a0al.: Deformable transformers for end-to-end object detection. In: arXiv preprint arXiv:2010.04159 (2020a)"},{"key":"2603_CR14","doi-asserted-by":"crossref","unstructured":"Dai, Z., Cai, B., Lin, Y., et\u00a0al.: Up-detr: Unsupervised pre-training for object detection with transformers. In: arXiv preprint arXiv:2011.09094 (2020b)","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"2603_CR15","doi-asserted-by":"crossref","unstructured":"Demisse, G.G., Papadopoulos, K., Aouada, D., et\u00a0al.: Pose encoding for robust skeleton-based action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 188\u2013194 (2018)","DOI":"10.1109\/CVPRW.2018.00056"},{"key":"2603_CR16","unstructured":"Devlin, J., Chang, M.W., Lee, K., et\u00a0al.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"2603_CR17","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: arXiv preprint arXiv:2010.11929 (2020)"},{"key":"2603_CR18","unstructured":"Du, Y., Wang, W., Wang, L.: Hierarchical recurrent neural network for skeleton based action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1110\u20131118 (2015)"},{"key":"2603_CR19","doi-asserted-by":"crossref","unstructured":"Duan, H., Zhao, Y., Chen, K., et\u00a0al.: Revisiting skeleton-based action recognition. arXiv preprint arXiv:2104.13586 (2021)","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"2603_CR20","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., et\u00a0al.: Slowfast networks for video recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"2603_CR21","doi-asserted-by":"crossref","unstructured":"Gao, X., Hu, W., Tang, J., et\u00a0al.: Optimized skeleton-based action recognition via sparsified graph regression. In: Proceedings of the 27th ACM international conference on multimedia, pp 601\u2013610 (2019)","DOI":"10.1145\/3343031.3351170"},{"key":"2603_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et\u00a0al.: Deep residual learning for image recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2603_CR23","doi-asserted-by":"crossref","unstructured":"Hu, Y., Liu, C., Li, Y., et\u00a0al.: Temporal perceptive network for skeleton-based action recognition. In: BMVC (2017)","DOI":"10.5244\/C.31.72"},{"key":"2603_CR24","unstructured":"Kay, W., Carreira, J., Simonyan, K., et\u00a0al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"2603_CR25","doi-asserted-by":"crossref","unstructured":"Ke, Q., Bennamoun, M., An, S., et\u00a0al.: A new representation of skeleton sequences for 3d action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3288\u20133297 (2017)","DOI":"10.1109\/CVPR.2017.486"},{"issue":"6","key":"2603_CR26","doi-asserted-by":"publisher","first-page":"2842","DOI":"10.1109\/TIP.2018.2812099","volume":"27","author":"Q Ke","year":"2018","unstructured":"Ke, Q., Bennamoun, M., An, S., et al.: Learning clip representations for skeleton-based 3d action recognition. IEEE Trans. Image Process. 27(6), 2842\u20132855 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"2603_CR27","doi-asserted-by":"crossref","unstructured":"Kim, T.S., Reiter, A.: Interpretable 3d human action analysis with temporal convolutional networks. In: 2017 IEEE conference on computer vision and pattern recognition workshops (CVPRW), IEEE, pp 1623\u20131631 (2017)","DOI":"10.1109\/CVPRW.2017.207"},{"key":"2603_CR28","unstructured":"Li, B., Dai, Y., Cheng, X., et\u00a0al.: Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep cnn. In: 2017 IEEE International conference on multimedia & expo workshops (ICMEW), IEEE, pp 601\u2013604 (2017a)"},{"key":"2603_CR29","unstructured":"Li, C., Zhong, Q., Xie, D., et\u00a0al.: Skeleton-based action recognition with convolutional neural networks. In: 2017 IEEE International conference on multimedia & Expo Workshops (ICMEW), IEEE, pp 597\u2013600 (2017b)"},{"key":"2603_CR30","doi-asserted-by":"crossref","unstructured":"Li, M., Chen, S., Chen, X., et\u00a0al.: Actional-structural graph convolutional networks for skeleton-based action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3595\u20133603 (2019)","DOI":"10.1109\/CVPR.2019.00371"},{"key":"2603_CR31","doi-asserted-by":"crossref","unstructured":"Li, M., Chen, S., Zhao, Y., et\u00a0al.: Dynamic multiscale graph neural networks for 3d skeleton based human motion prediction. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 214\u2013223 (2020)","DOI":"10.1109\/CVPR42600.2020.00029"},{"key":"2603_CR32","doi-asserted-by":"crossref","unstructured":"Liu, J., Shahroudy, A., Xu, D., et\u00a0al.: Spatio-temporal lstm with trust gates for 3d human action recognition. In: European conference on computer vision, Springer, Berlin pp 816\u2013833 (2016)","DOI":"10.1007\/978-3-319-46487-9_50"},{"key":"2603_CR33","doi-asserted-by":"crossref","unstructured":"Liu, J., Wang, G., Hu, P., et\u00a0al.: Global context-aware attention lstm networks for 3d action recognition. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 1647\u20131656 (2017a)","DOI":"10.1109\/CVPR.2017.391"},{"key":"2603_CR34","doi-asserted-by":"crossref","unstructured":"Liu, J., Shahroudy, A., Perez, M., et\u00a0al.: Ntu rgb+d 120: A large-scale benchmark for 3d human activity understanding. In: CoRR, abs\/1905.04757 (2019)","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"2603_CR35","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1016\/j.patcog.2017.02.030","volume":"68","author":"M Liu","year":"2017","unstructured":"Liu, M., Liu, H., Chen, C.: Enhanced skeleton visualization for view invariant human action recognition. Patt. Recognit. 68, 346\u2013362 (2017)","journal-title":"Patt. Recognit."},{"issue":"6","key":"2603_CR36","doi-asserted-by":"publisher","first-page":"1053","DOI":"10.1007\/s00371-018-1556-0","volume":"34","author":"C Ma","year":"2018","unstructured":"Ma, C., Wang, A., Chen, G., et al.: Hand joints-based gesture recognition for noisy dataset using nested interval unscented Kalman filter with LSTM network. Visual Comp. 34(6), 1053\u20131063 (2018)","journal-title":"Visual Comp."},{"issue":"8","key":"2603_CR37","doi-asserted-by":"publisher","first-page":"1979","DOI":"10.1109\/TPAMI.2018.2858821","volume":"41","author":"T Miyato","year":"2018","unstructured":"Miyato, T., Si, Maeda, Koyama, M., et al.: Virtual adversarial training: a regularization method for supervised and semi-supervised learning. IEEE Trans. Patt. Anal. Mach. Intell. 41(8), 1979\u20131993 (2018)","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell."},{"key":"2603_CR38","unstructured":"Parmar, N., Vaswani, A., Uszkoreit, J., et\u00a0al.: Image transformer. In: arXiv preprint arXiv:1802.05751 (2020)"},{"key":"2603_CR39","unstructured":"Paszke, A., Gross, S., Massa, F., et\u00a0al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in neural information processing systems, pp 8026\u20138037 (2019)"},{"key":"2603_CR40","doi-asserted-by":"crossref","unstructured":"Peng, G., Wang, S.: Dual semi-supervised learning for facial action unit recognition. In: Proceedings of the AAAI conference on artificial intelligence, pp 8827\u20138834 (2019)","DOI":"10.1609\/aaai.v33i01.33018827"},{"key":"2603_CR41","doi-asserted-by":"crossref","unstructured":"Peng, W., Hong, X., Chen, H., et\u00a0al.: Learning graph convolutional network for skeleton-based human action recognition by neural searching. In: Proceedings of the AAAI conference on artificial intelligence (2020)","DOI":"10.1609\/aaai.v34i03.5652"},{"issue":"103","key":"2603_CR42","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1016\/j.cviu.2021.103219","volume":"208\u2013209","author":"C Plizzari","year":"2021","unstructured":"Plizzari, C., Cannici, M., Matteucci, M.: Skeleton-based action recognition via spatial and temporal transformer networks. Comp. Vis. Image Understand. 208\u2013209(103), 219 (2021). https:\/\/doi.org\/10.1016\/j.cviu.2021.103219","journal-title":"Comp. Vis. Image Understand."},{"key":"2603_CR43","doi-asserted-by":"crossref","unstructured":"Shahroudy, A., Liu, J., Ng, T.T., et\u00a0al.: Ntu rgb+ d: A large scale dataset for 3d human activity analysis. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1010\u20131019 (2016)","DOI":"10.1109\/CVPR.2016.115"},{"key":"2603_CR44","doi-asserted-by":"crossref","unstructured":"Shi, L., Zhang, Y., Cheng, J., et\u00a0al.: Skeleton-based action recognition with directed graph neural networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7912\u20137921 (2019)","DOI":"10.1109\/CVPR.2019.00810"},{"key":"2603_CR45","doi-asserted-by":"crossref","unstructured":"Shi, L., Zhang, Y., Cheng, J., et\u00a0al.: Two-stream adaptive graph convolutional networks for skeleton-based action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 12,026\u201312,035 (2019)","DOI":"10.1109\/CVPR.2019.01230"},{"key":"2603_CR46","doi-asserted-by":"crossref","unstructured":"Si, C., Jing, Y., Wang, W., et\u00a0al.: Skeleton-based action recognition with spatial reasoning and temporal stack learning. In: Proceedings of the European conference on computer vision (ECCV), pp 103\u2013118 (2018)","DOI":"10.1007\/978-3-030-01246-5_7"},{"key":"2603_CR47","doi-asserted-by":"crossref","unstructured":"Si, C., Chen, W., Wang, W., et\u00a0al.: An attention enhanced graph convolutional lstm network for skeleton-based action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1227\u20131236 (2019)","DOI":"10.1109\/CVPR.2019.00132"},{"key":"2603_CR48","doi-asserted-by":"crossref","unstructured":"Si, C., Nie, X., Wang, W., et\u00a0al.: Adversarial self-supervised learning for semi-supervised 3d action recognition. In: Proceedings of the European conference on computer vision (ECCV), pp 35\u201351 (2020)","DOI":"10.1007\/978-3-030-58571-6_3"},{"key":"2603_CR49","doi-asserted-by":"crossref","unstructured":"Song, S., Lan, C., Xing, J., et\u00a0al.: An end-to-end spatio-temporal attention model for human action recognition from skeleton data. In: Thirty-first AAAI conference on artificial intelligence (2017)","DOI":"10.1609\/aaai.v31i1.11212"},{"issue":"7","key":"2603_CR50","doi-asserted-by":"publisher","first-page":"3459","DOI":"10.1109\/TIP.2018.2818328","volume":"27","author":"S Song","year":"2018","unstructured":"Song, S., Lan, C., Xing, J., et al.: Spatio-temporal attention-based LSTM networks for 3d action recognition and detection. IEEE Trans. Image Process. 27(7), 3459\u20133471 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"2603_CR51","doi-asserted-by":"crossref","unstructured":"Straka, M., Hauswiesner, S., R\u00fcther, M., et\u00a0al.: Skeletal graph based human pose estimation in real-time. In: BMVC, pp 1\u201312 (2011)","DOI":"10.5244\/C.25.69"},{"key":"2603_CR52","doi-asserted-by":"crossref","unstructured":"Sun, Z., Cao, S., Yang, Y., et\u00a0al.: Rethinking transformer-based set prediction for object detection. In: arXiv preprint arXiv:2011.10881 (2020)","DOI":"10.1109\/ICCV48922.2021.00359"},{"key":"2603_CR53","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/j.patcog.2018.01.020","volume":"79","author":"Z Tu","year":"2018","unstructured":"Tu, Z., Xie, W., Qin, Q., et al.: Multi-stream CNN: learning representations based on human-related regions for action recognition. Patt. Recogn. 79, 32\u201343 (2018)","journal-title":"Patt. Recogn."},{"key":"2603_CR54","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et\u00a0al.: Attention is all you need. In: Advances in neural information processing systems, pp 5998\u20136008 (2017)"},{"key":"2603_CR55","doi-asserted-by":"crossref","unstructured":"Vemulapalli, R., Chellapa, R.: Rolling rotations for recognizing human actions from 3d skeletal data. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4471\u20134479 (2016)","DOI":"10.1109\/CVPR.2016.484"},{"key":"2603_CR56","doi-asserted-by":"crossref","unstructured":"Vemulapalli, R., Arrate, F., Chellappa, R.: Human action recognition by representing 3d skeletons as points in a lie group. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 588\u2013595 (2014)","DOI":"10.1109\/CVPR.2014.82"},{"issue":"9","key":"2603_CR57","doi-asserted-by":"publisher","first-page":"4382","DOI":"10.1109\/TIP.2018.2837386","volume":"27","author":"H Wang","year":"2018","unstructured":"Wang, H., Wang, L.: Beyond joints: Learning representations from primitive geometries for skeleton-based action recognition and detection. IEEE Trans. Image Process. 27(9), 4382\u20134394 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"2603_CR58","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xu, Z., Wang, X., et\u00a0al.: End-to-end video instance segmentation with transformers. In: arXiv preprint arXiv:2011.14503 (2020)","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"2603_CR59","doi-asserted-by":"crossref","unstructured":"Wen, Y.H., Gao, L., Fu, H., et\u00a0al.: Graph CNNS with motif and variable temporal block for skeleton-based action recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp 8989\u20138996 (2019)","DOI":"10.1609\/aaai.v33i01.33018989"},{"key":"2603_CR60","unstructured":"Wu, B., Xu, C., Dai, X., et\u00a0al.: Visual transformers: token-based image representation and processing for computer vision. In: arXiv preprint arXiv:2006.03677 (2020)"},{"issue":"10","key":"2603_CR61","doi-asserted-by":"publisher","first-page":"2951","DOI":"10.1109\/TNNLS.2018.2886008","volume":"30","author":"Z Xu","year":"2019","unstructured":"Xu, Z., Hu, R., Chen, J., et al.: Semisupervised discriminant multimanifold analysis for action recognition. IEEE Trans. Neur. Netw. Learn Sys. 30(10), 2951\u20132962 (2019)","journal-title":"IEEE Trans. Neur. Netw. Learn Sys."},{"key":"2603_CR62","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Thirty-second AAAI conference on artificial intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"2603_CR63","doi-asserted-by":"crossref","unstructured":"Yang, F., Yang, H., Fu, J., et\u00a0al.: Learning texture transformer network for image super-resolution. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, pp 5791\u20135800 (2020)","DOI":"10.1109\/CVPR42600.2020.00583"},{"issue":"4","key":"2603_CR64","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1109\/JAS.2017.7510625","volume":"4","author":"X Yuan","year":"2017","unstructured":"Yuan, X., Kong, L., Feng, D., et al.: Automatic feature point detection and tracking of human actions in time-of-flight videos. IEEE\/CAA J. Automat. Sinica. 4(4), 677\u2013685 (2017). https:\/\/doi.org\/10.1109\/JAS.2017.7510625","journal-title":"IEEE\/CAA J. Automat. Sinica."},{"key":"2603_CR65","doi-asserted-by":"crossref","unstructured":"Zeng, Y., Fu, J., Chao, H.: Learning joint spatial-temporal transformations for video inpainting. In: Proceedings of the European conference on computer vision (ECCV), pp 528\u2013543 (2020)","DOI":"10.1007\/978-3-030-58517-4_31"},{"issue":"1","key":"2603_CR66","doi-asserted-by":"publisher","first-page":"59","DOI":"10.3390\/s19010059","volume":"19","author":"N Zengeler","year":"2019","unstructured":"Zengeler, N., Kopinski, T., Handmann, U.: Hand gesture recognition in automotive human-machine interaction using depth cameras. Sensors 19(1), 59 (2019)","journal-title":"Sensors"},{"issue":"107","key":"2603_CR67","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1007\/978-3-030-41404-7_22","volume":"103","author":"D Zhang","year":"2020","unstructured":"Zhang, D., He, L., Tu, Z., et al.: Learning motion representation for real-time spatio-temporal action localization. Patt. Recogn. 103(107), 312 (2020)","journal-title":"Patt. Recogn."},{"issue":"4","key":"2603_CR68","doi-asserted-by":"publisher","first-page":"960","DOI":"10.1109\/TCYB.2016.2535122","volume":"47","author":"J Zhang","year":"2016","unstructured":"Zhang, J., Han, Y., Tang, J., et al.: Semi-supervised image-to-video adaptation for video action recognition. IEEE Trans. Cybernet. 47(4), 960\u2013973 (2016)","journal-title":"IEEE Trans. Cybernet."},{"key":"2603_CR69","doi-asserted-by":"crossref","unstructured":"Zhang, J., Ye, G., Tu, Z., et\u00a0al.: A spatial attentive and temporal dilated (satd) gcn for skeleton-based action recognition. CAAI Transactions on intelligence technology pp 1\u201310 (2021a)","DOI":"10.1049\/cit2.12012"},{"issue":"8","key":"2603_CR70","doi-asserted-by":"publisher","first-page":"1963","DOI":"10.1109\/TPAMI.2019.2896631","volume":"41","author":"P Zhang","year":"2019","unstructured":"Zhang, P., Lan, C., Xing, J., et al.: View adaptive neural networks for high performance skeleton-based human action recognition. IEEE Trans. Patt. Anal. Mach. Intell. 41(8), 1963\u20131978 (2019)","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell."},{"key":"2603_CR71","doi-asserted-by":"crossref","unstructured":"Zhang, P., Lan, C., Zeng, W., et\u00a0al.: Semantics-guided neural networks for efficient skeleton-based human action recognition. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, pp 1112\u20131121 (2020c)","DOI":"10.1109\/CVPR42600.2020.00119"},{"key":"2603_CR72","doi-asserted-by":"crossref","unstructured":"Zhang, X., Xu, C., Tian, X., et al.: Graph edge convolutional neural networks for skeleton-based action recognition. IEEE Trans. Neur. Netw. Learn Sys. 31(8), 3047\u20133060 (2019)","DOI":"10.1109\/TNNLS.2019.2935173"},{"key":"2603_CR73","doi-asserted-by":"crossref","unstructured":"Zhang, X., Xu, C., Tao, D.: Context aware graph convolution for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 14,333\u201314,342 (2020d)","DOI":"10.1109\/CVPR42600.2020.01434"},{"key":"2603_CR74","unstructured":"Zhang, X., Li, C., Shi, H., et\u00a0al.: Adapnet: adaptability decomposing encoder-decoder network for weakly supervised action recognition and localization. IEEE Transactions on Neural Networks and Learning Systems (2020e)"},{"key":"2603_CR75","unstructured":"Zhao, H., Jiang, L., Jia, J., et\u00a0al.: Point transformer. In: arXiv preprint arXiv:2012.09164 (2020)"},{"key":"2603_CR76","doi-asserted-by":"crossref","unstructured":"Zhao, R., Wang, K., Su, H., et\u00a0al.: Bayesian graph convolution lstm for skeleton based action recognition. In: Proceedings of the IEEE international conference on computer vision, pp 6882\u20136892 (2019)","DOI":"10.1109\/ICCV.2019.00698"},{"key":"2603_CR77","doi-asserted-by":"crossref","unstructured":"Zheng, N., Wen, J., Liu, R., et\u00a0al.: Unsupervised representation learning with long-term dynamics for skeleton based action recognition. In: Thirty-Second AAAI conference on artificial intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11853"},{"key":"2603_CR78","doi-asserted-by":"crossref","unstructured":"Zheng, W., Li, L., Zhang, Z., et\u00a0al.: Relational network for skeleton-based action recognition. In: 2019 IEEE International conference on multimedia and expo (ICME), pp 826\u2013831 (2019)","DOI":"10.1109\/ICME.2019.00147"},{"key":"2603_CR79","doi-asserted-by":"crossref","unstructured":"Zhou, L., Zhou, Y., Corso, J.J., et\u00a0al.: End-to-end dense video captioning with masked transformer. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8739\u20138748 (2018)","DOI":"10.1109\/CVPR.2018.00911"},{"issue":"11","key":"2603_CR80","doi-asserted-by":"publisher","first-page":"2977","DOI":"10.1109\/TMM.2019.2962304","volume":"22","author":"K Zhu","year":"2019","unstructured":"Zhu, K., Wang, R., Zhao, Q., et al.: A cuboid CNN model with an attention mechanism for skeleton-based action recognition. IEEE Trans. Multim. 22(11), 2977\u20132989 (2019)","journal-title":"IEEE Trans. Multim."}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-022-02603-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-022-02603-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-022-02603-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T09:06:56Z","timestamp":1695978416000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-022-02603-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,26]]},"references-count":80,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["2603"],"URL":"https:\/\/doi.org\/10.1007\/s00371-022-02603-1","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,26]]},"assertion":[{"value":"14 June 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 July 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}